enmanuelmag/heimdall-mcp
Transparent proxy for any MCP server that intercepts all JSON-RPC messages, measures latency, and stores traces in SQLite, PostgreSQL, or MySQL. Exports OpenTelemetry (OTLP) spans to Jaeger, Tempo, or Grafana. Supports stdio, HTTP, and SSE transports. npx @cardor/heimdall-mcp
Ads
Overview
Transparent proxy for any MCP server. Intercepts all JSON-RPC messages, measures latency, stores traces in a configurable database, and enforces per-server allow/deny policies — without touching the original server.
Installation
npx @cardor/heimdall-mcp
Configuration
{
"mcpServers": {
"heimdall-mcp": {
"command": "npx",
"args": [
"@modelcontextprotocol/server-filesystem",
"/tmp"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Tags
- awesome-list
Related MCP servers
Monitoring
cloudsealed/cloudsealed-mcp
Two deterministic, rule-based analysis engines for agents: cloud billing cost anomaly detection (rolling-median + MAD, resistant to the masking effect) and auditable architecture risk scoring (single point of failure, coupling, scalability gap) with a rule-by-rule breakdown for every score. `uvx cloudsealed-mcp`
Monitoring
arsentev-ai/contextburn
Run efficiency for Claude Code sessions: the share of paid tokens that became model output versus re-reading context already sent, by tokens and cost-weighted. Reads local transcripts, makes no network calls.
Monitoring
seancrecord/scvd-general-store-repo (scvd-tab)
Agent tool spend tracker. Local JSONL storage, consent-gated, nothing leaves the file. Free MCP server. `npx scvd-tab`
Monitoring
FailEcho/failecho
Cross-agent failure intelligence. Before an agent retries a failed tool call, `check_tool_failure` reports whether other agents are hitting the same failure right now and which recovery actually worked, with a Wilson-score confidence. Privacy-by-schema: no prompts, keys, or payloads stored. Hosted remote server at `https://failecho.com/mcp`, or self-host.
Monitoring
AIops-tools/Endpoint-AIops
Governed managed-endpoint fleet operations (thin-client/VDI) — login-storm and patch/config-drift analysis, inventory, and guardrailed remediation (13 tools) with unbypassable audit logging (MCP + CLI), budget/runaway guards, and undo/rollback.
Monitoring
magna-nz/tallybook
Prices every Claude Code and Codex session already on disk and lets the agent ask what it's spending mid-session: cost by session, sub-agent and model, week-on-week comparison, and plain-English findings with applyable patches. No proxy, no API key, nothing leaves the machine. Install: `brew install --cask magna-nz/tap/tallybook`.
Monitoring
iris-eval/mcp-server
Iris scores every agent run for quality, safety, and cost — on your machine, with no SDK and no account. Most agent projects check quality by running a few remembered prompts and eyeballing the output. Iris replaces that with numbers you can audit: your agent's runs land in a SQLite database on your disk, 13 built-in rules score them deterministically — PII, prompt injection, hallucination markers, cost thresholds — free, with no LLM calls, and an optional LLM judge with a hard per-eval cost cap handles the semantic questions. Every rule is inspectable and editable, because a judge you can't audit is just vibes with a number on it. MIT licensed, no telemetry; your traces never leave your machine.
6 tools · deploy_rule, evaluate_output
Monitoring
last9/last9-mcp-server
Your AI agent doesn't know what's broken in production. This fixes that. Last9 MCP Server connects Claude, Cursor, Windsurf, and any other MCP-capable AI assistant directly to your production observability data — logs, metrics, traces, exceptions, database queries, alerts, and deployments. The agent stops guessing and starts reading the actual signal. No binary to install. No tokens to manage. One URL, OAuth in your browser, done. Find your org slug in your Last9 URL: app.last9.io/<org_slug>/... Type /mcp, select last9, authenticate. That's it.
6 tools · get_alerts, get_database_slow_queries